Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    digest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _goal
    -0.07
     nonlinear
    -0.07
     marched
    -0.07
     Linear
    -0.07
    kara
    -0.07
     tree
    -0.07
    222
    -0.07
    _cores
    -0.07
    _control
    -0.07
    rání
    -0.07
    POSITIVE LOGITS
     Digest
    0.15
     digest
    0.12
    Digest
    0.12
    digest
    0.10
    igest
    0.09
     digestion
    0.09
    _digest
    0.08
     diet
    0.08
    ест
    0.08
     ingest
    0.07
    Act Density 0.004%

    No Known Activations